CN107730508A - Color documents images multichannel binary processing method - Google Patents
Color documents images multichannel binary processing method Download PDFInfo
- Publication number
- CN107730508A CN107730508A CN201710780085.3A CN201710780085A CN107730508A CN 107730508 A CN107730508 A CN 107730508A CN 201710780085 A CN201710780085 A CN 201710780085A CN 107730508 A CN107730508 A CN 107730508A
- Authority
- CN
- China
- Prior art keywords
- images
- gray
- width
- color documents
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
Abstract
Present invention is disclosed a kind of color documents images multichannel binary processing method, extracts the gray value of color documents images triple channel respectively, obtains three width gray level images of the coloured image;Partitioned binarization is carried out respectively to three width gray level images, obtains three width binary images;Three width binary images are merged into a width binary image.Color documents images multichannel binary processing method proposed by the present invention, gray level image is obtained by extracting the gray value of color documents images triple channel respectively, remain whole colouring informations of color documents images, the shortcomings that losing a large amount of color informations during prior art coloured image gray processing is overcome, improves the accuracy that gray-scale map turns binary picture.The present invention synthesizes a width bianry image, is effectively utilized triple channel all colours information so that binaryzation result of the present invention is more accurate, and has certain anti-noise ability by carrying out threshold determination to each pixel of the respective binary image of triple channel.
Description
Technical field
The invention belongs to technical field of image processing, is related to a kind of image processing method, more particularly to a kind of in colored text
This image multichannel binary processing method.
Background technology
Binaryzation is the basic operation of image procossing, and only two kinds of colors of black and white are included for pending image to be converted to
Bianry image, reduce image data amount, to highlight the profile of target interested.With digital image processing techniques
Fast development, binaryzation application is also more and more extensive, also more and more important.For example, in OCR (Optical Character
Recognition, optical character identification) in system, the quality of binary conversion treatment effect has a strong impact on the accuracy rate of OCR identifications.
At present, common binarization method is:First by coloured image gray processing, conventional gray processing method is by cromogram
Triple channel gray scale as in is averaging to obtain a gray value;A global threshold is set to gray level image again, with the global threshold
The data of gray level image are divided into two parts by value:Pixel group more than global threshold and the pixel group less than global threshold;Will be big
It is set as white (or black) in the pixel value of the pixel group of global threshold, less than the pixel value setting of the pixel group of global threshold
For black (or white).However, the method being averaging to the triple channel gray scale of coloured image can lose great amount of images useful information,
And when the luminance background color or uneven foreground color of pending image, target image is entered using a global threshold
The poor effect of row binaryzation.
In view of this, nowadays there is an urgent need to design a kind of new image processing method, to overcome conventional images processing side
Drawbacks described above existing for method.
The content of the invention
The technical problems to be solved by the invention are:A kind of color documents images multichannel binary processing method is provided,
Gray-scale map can be improved and turn binary picture accuracy.
In order to solve the above technical problems, the present invention adopts the following technical scheme that:
A kind of color documents images multichannel binary processing method, the gray scale of color documents images triple channel is extracted respectively
Value, obtains three width gray level images of the coloured image;Partitioned binarization is carried out respectively to three width gray level images, obtains three width two-values
Change image;Three width binary images are merged into a width binary image;
Methods described comprises the following steps:
Step S1, color documents images are read in;
The color documents images for treating binaryzation are read in, its size is M × N × 3, and M, N represent color documents images respectively
Line number and columns, 3 represent three Color Channels of color documents images, are respectively red, green, blueness;
Step S2, gray-scale map is obtained;
The gray value of color documents images triple channel is extracted respectively;Obtain the width gray-scale map of gray_r, gray_g, gray_b tri-
Picture;
Step S3, gray-scale map partitioned binarization;
Step S4, binary image is obtained;
- step S41, define a size and color documents images identical null matrix D;
- step S42, according to the following formula, to matrix D assignment
Wherein, (p, q) be matrix D in element coordinate, p=1,2 ... M, q=1,2 ... N, R (p, q), G (p, q), B
(p, q) represents binary image R, G, B element coordinate respectively;
In step S3, described gray-scale map partitioned binarization comprises the following steps that:
Step S31, it is 16 × 16 elements to set window size, since first pixel of gray level image, to gray level image
Adding window;
Step S32, the average gray value T in calculation window, the threshold value using T as pixel binaryzation in window;
Step S33, to each pixel binaryzation in window, when pixel value is more than or equal to T, then it is 255 to change pixel value,
When pixel value is less than T, then it is 0 to change pixel value;
Step S34, window is step-length with 16, travels through view picture gray level image, until all pixels are binarized, obtains three width
Binary image, respectively R, G, B.
A kind of color documents images multichannel binary processing method, the gray scale of color documents images triple channel is extracted respectively
Value, obtains three width gray level images of the coloured image;Partitioned binarization is carried out respectively to three width gray level images, obtains three width two-values
Change image;Three width binary images are merged into a width binary image.
As a preferred embodiment of the present invention, methods described comprises the following steps:
Step S1, color documents images are read in;
The color documents images for treating binaryzation are read in, its size is M × N × 3, and M, N represent color documents images respectively
Line number and columns, 3 represent three Color Channels of color documents images, are respectively red, green, blueness;
Step S2, gray-scale map is obtained;
The gray value of color documents images triple channel is extracted respectively;Obtain the width gray-scale map of gray_r, gray_g, gray_b tri-
Picture;
Step S3, gray-scale map partitioned binarization;
Step S4, binary image is obtained;
- step S41, define a size and color documents images identical null matrix D;
- step S42, according to the following formula, to matrix D assignment
Wherein, (p, q) be matrix D in element coordinate, p=1,2 ... M, q=1,2 ... N, R (p, q), G (p, q), B
(p, q) represents binary image R, G, B element coordinate respectively.
As a preferred embodiment of the present invention, in step S3, the specific steps of described gray-scale map partitioned binarization are such as
Under:
Step S31, it is 16 × 16 elements to set window size, since first pixel of gray level image, to gray level image
Adding window;
Step S32, the average gray value T in calculation window, the threshold value using T as pixel binaryzation in window;
Step S33, to each pixel binaryzation in window, when pixel value is more than or equal to T, then it is 255 to change pixel value,
When pixel value is less than T, then it is 0 to change pixel value;
Step S34, window is step-length with 16, travels through view picture gray level image, until all pixels are binarized, obtains three width
Binary image, respectively R, G, B.
The beneficial effects of the present invention are:Color documents images multichannel binary processing method proposed by the present invention, lead to
Undue you can well imagine takes the gray value of color documents images triple channel to obtain gray level image, remains whole face of color documents images
Color information, overcome the shortcomings that lost a large amount of color informations during prior art coloured image gray processing so that the present invention
Turn the advantages of binary picture accuracy is high with gray-scale map.
The present invention synthesizes a width two-value by carrying out threshold determination to each pixel of the respective binary image of triple channel
Image, it is effectively utilized triple channel all colours information so that binaryzation result of the present invention is more accurate, and has certain anti-noise
Ability.
Brief description of the drawings
Fig. 1 is the flow chart of color documents images multichannel binary processing method of the present invention.
Embodiment
The preferred embodiment that the invention will now be described in detail with reference to the accompanying drawings.
Embodiment one
Present invention is disclosed a kind of color documents images multichannel binary processing method, color documents images are extracted respectively
The gray value of triple channel, obtain three width gray level images of the coloured image;Partitioned binarization is carried out respectively to three width gray level images,
Obtain three width binary images;Three width binary images are merged into a width binary image.Due to the three of color documents images
Passage gray value is obtained for sufficient utilization, therefore binaryzation result is more accurate.
Referring to Fig. 1, methods described specifically comprises the following steps:
【Step S1】Read in color documents images;
The color documents images for treating binaryzation are read in, its size is M × N × 3, and M, N represent color documents images respectively
Line number and columns, 3 represent three Color Channels of color documents images, are respectively red, green, blueness;
【Step S2】Obtain gray-scale map;
The gray value of color documents images triple channel is extracted respectively;Obtain the width gray-scale map of gray_r, gray_g, gray_b tri-
Picture;
【Step S3】Gray-scale map partitioned binarization;Comprise the following steps that:
Step S31, it is 16 × 16 elements to set window size, since first pixel of gray level image, to gray level image
Adding window;
Step S32, the average gray value T in calculation window, the threshold value using T as pixel binaryzation in window;
Step S33, to each pixel binaryzation in window, when pixel value is more than or equal to T, then it is 255 to change pixel value,
When pixel value is less than T, then it is 0 to change pixel value;
Step S34, window is step-length with 16, travels through view picture gray level image, until all pixels are binarized, obtains three width
Binary image, respectively R, G, B.
【Step S4】Obtain binary image;
- step S41, define a size and color documents images identical null matrix D;
- step S42, according to the following formula, to matrix D assignment
Wherein, (p, q) be matrix D in element coordinate, p=1,2 ... M, q=1,2 ... N, R (p, q), G (p, q), B
(p, q) represents binary image R, G, B element coordinate respectively.
In summary, color documents images multichannel binary processing method proposed by the present invention, by extracting coloured silk respectively
The gray value of color text image triple channel obtains gray level image, remains whole colouring informations of color documents images, overcomes
The shortcomings that a large amount of color informations being lost during prior art coloured image gray processing so that the present invention turns with gray-scale map
The advantages of binary picture accuracy is high.
The present invention synthesizes a width two-value by carrying out threshold determination to each pixel of the respective binary image of triple channel
Image, it is effectively utilized triple channel all colours information so that binaryzation result of the present invention is more accurate, and has certain anti-noise
Ability.
Here description of the invention and application are illustrative, are not wishing to limit the scope of the invention to above-described embodiment
In.The deformation and change of embodiments disclosed herein are possible, real for those skilled in the art
The replacement and equivalent various parts for applying example are known.It should be appreciated by the person skilled in the art that the present invention is not being departed from
Spirit or essential characteristics in the case of, the present invention can in other forms, structure, arrangement, ratio, and with other components,
Material and part are realized.In the case where not departing from scope and spirit of the present invention, embodiments disclosed herein can be entered
The other deformations of row and change.
Claims (3)
1. a kind of color documents images multichannel binary processing method, it is characterised in that extract color documents images three respectively
The gray value of passage, obtain three width gray level images of the coloured image;Partitioned binarization is carried out respectively to three width gray level images, obtained
To three width binary images;Three width binary images are merged into a width binary image;
Methods described comprises the following steps:
Step S1, color documents images are read in;
The color documents images for treating binaryzation are read in, its size is M × N × 3, and M, N represent the line number of color documents images respectively
Three Color Channels of color documents images are represented with columns, 3, are respectively red, green, blueness;
Step S2, gray-scale map is obtained;
The gray value of color documents images triple channel is extracted respectively;Obtain the width gray level image of gray_r, gray_g, gray_b tri-;
Step S3, gray-scale map partitioned binarization;
Step S4, binary image is obtained;
- step S41, define a size and color documents images identical null matrix D;
- step S42, according to the following formula, to matrix D assignment
Wherein, (p, q) be matrix D in element coordinate, p=1,2 ... M, q=1,2 ... N, R (p, q), G (p, q), B (p, q)
Binary image R, G, B element coordinate are represented respectively;
In step S3, described gray-scale map partitioned binarization comprises the following steps that:
Step S31, it is 16 × 16 elements to set window size, since first pixel of gray level image, to gray level image adding window;
Step S32, the average gray value T in calculation window, the threshold value using T as pixel binaryzation in window;
Step S33, to each pixel binaryzation in window, when pixel value is more than or equal to T, then it is 255 to change pixel value, works as picture
Element value is less than T, then it is 0 to change pixel value;
Step S34, window is step-length with 16, travels through view picture gray level image, until all pixels are binarized, obtains three width two-values
Change image, respectively R, G, B.
2. a kind of color documents images multichannel binary processing method, it is characterised in that extract color documents images three respectively
The gray value of passage, obtain three width gray level images of the coloured image;Partitioned binarization is carried out respectively to three width gray level images, obtained
To three width binary images;Three width binary images are merged into a width binary image.
3. color documents images multichannel binary processing method according to claim 2, it is characterised in that:
Methods described comprises the following steps:
Step S1, color documents images are read in;
The color documents images for treating binaryzation are read in, its size is M × N × 3, and M, N represent the line number of color documents images respectively
Three Color Channels of color documents images are represented with columns, 3, are respectively red, green, blueness;
Step S2, gray-scale map is obtained;
The gray value of color documents images triple channel is extracted respectively;Obtain the width gray level image of gray_r, gray_g, gray_b tri-;
Step S3, gray-scale map partitioned binarization;
Step S4, binary image is obtained;
- step S41, define a size and color documents images identical null matrix D;
- step S42, according to the following formula, to matrix D assignment
Wherein, (p, q) be matrix D in element coordinate, p=1,2 ... M, q=1,2 ... N, R (p, q), G (p, q), B (p, q)
Binary image R, G, B element coordinate are represented respectively.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710780085.3A CN107730508A (en) | 2017-09-01 | 2017-09-01 | Color documents images multichannel binary processing method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710780085.3A CN107730508A (en) | 2017-09-01 | 2017-09-01 | Color documents images multichannel binary processing method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107730508A true CN107730508A (en) | 2018-02-23 |
Family
ID=61205405
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710780085.3A Pending CN107730508A (en) | 2017-09-01 | 2017-09-01 | Color documents images multichannel binary processing method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107730508A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108229436A (en) * | 2018-02-02 | 2018-06-29 | 杭州清本科技有限公司 | Coloured image gray processing method and device, storage medium for certificate identification |
CN109949210A (en) * | 2019-03-07 | 2019-06-28 | 北京麦哲科技有限公司 | A kind of removing method and device of scan image background |
CN110763682A (en) * | 2019-09-19 | 2020-02-07 | 湖北三江航天万峰科技发展有限公司 | Method and system for detecting surface glaze shortage of ceramic tile |
CN112508038A (en) * | 2020-12-03 | 2021-03-16 | 江苏科技大学 | Cross-channel local binary pattern color texture classification method |
CN116303909A (en) * | 2023-04-26 | 2023-06-23 | 山东齐鲁电子招标采购服务有限公司 | Matching method, equipment and medium for electronic bidding documents and clauses |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130121575A1 (en) * | 2011-11-11 | 2013-05-16 | Seoul National University R&B Foundation | Image analysis apparatus using main color and method of controlling the same |
CN103914687A (en) * | 2014-03-14 | 2014-07-09 | 常州大学 | Rectangular-target identification method based on multiple channels and multiple threshold values |
CN104504662A (en) * | 2014-12-26 | 2015-04-08 | 北京慧眼智行科技有限公司 | Homomorphic filtering based image processing method and system |
-
2017
- 2017-09-01 CN CN201710780085.3A patent/CN107730508A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130121575A1 (en) * | 2011-11-11 | 2013-05-16 | Seoul National University R&B Foundation | Image analysis apparatus using main color and method of controlling the same |
CN103914687A (en) * | 2014-03-14 | 2014-07-09 | 常州大学 | Rectangular-target identification method based on multiple channels and multiple threshold values |
CN104504662A (en) * | 2014-12-26 | 2015-04-08 | 北京慧眼智行科技有限公司 | Homomorphic filtering based image processing method and system |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108229436A (en) * | 2018-02-02 | 2018-06-29 | 杭州清本科技有限公司 | Coloured image gray processing method and device, storage medium for certificate identification |
CN109949210A (en) * | 2019-03-07 | 2019-06-28 | 北京麦哲科技有限公司 | A kind of removing method and device of scan image background |
CN110763682A (en) * | 2019-09-19 | 2020-02-07 | 湖北三江航天万峰科技发展有限公司 | Method and system for detecting surface glaze shortage of ceramic tile |
CN112508038A (en) * | 2020-12-03 | 2021-03-16 | 江苏科技大学 | Cross-channel local binary pattern color texture classification method |
CN112508038B (en) * | 2020-12-03 | 2022-11-08 | 江苏科技大学 | Cross-channel local binary pattern color texture classification method |
CN116303909A (en) * | 2023-04-26 | 2023-06-23 | 山东齐鲁电子招标采购服务有限公司 | Matching method, equipment and medium for electronic bidding documents and clauses |
CN116303909B (en) * | 2023-04-26 | 2023-08-22 | 山东齐鲁电子招标采购服务有限公司 | Matching method, equipment and medium for electronic bidding documents and clauses |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107730508A (en) | Color documents images multichannel binary processing method | |
CN106682629B (en) | Identification algorithm for identity card number under complex background | |
CN105740860A (en) | Automatic detection method for Chinese character area of shop sign in natural scene | |
CN103020917B (en) | Method for restoring ancient Chinese calligraphy and painting images on basis of conspicuousness detection | |
CN1312625C (en) | Character extracting method from complecate background color image based on run-length adjacent map | |
CN103093203A (en) | Human body re-recognition method and human body re-recognition system | |
CN106096610A (en) | A kind of file and picture binary coding method based on support vector machine | |
CN108921120B (en) | Cigarette identification method suitable for wide retail scene | |
CN101295359A (en) | Image processing program and image processing apparatus | |
CN105005766A (en) | Vehicle body color identification method | |
CN109740572A (en) | A kind of human face in-vivo detection method based on partial color textural characteristics | |
CN108711160B (en) | Target segmentation method based on HSI (high speed input/output) enhanced model | |
CN106446885A (en) | Paper-based Braille recognition method and system | |
CN116468640B (en) | Video image enhancement method for Internet teaching | |
CN104751446A (en) | Digital pattern feature based tie-dyeing process prediction method | |
CN111260645A (en) | Method and system for detecting tampered image based on block classification deep learning | |
CN112215781B (en) | Improved local binarization method | |
CN110400320B (en) | Segmentation method of electrowetting defective pixels | |
CN106815580A (en) | A kind of license plate locating method | |
CN116189194B (en) | Drawing enhancement segmentation method for engineering modeling | |
CN116109933B (en) | Dynamic identification method for ecological restoration of abandoned mine | |
CN105574837A (en) | Image similarity matching method and device | |
CN111241916A (en) | Method for establishing traffic sign recognition model | |
CN111414960A (en) | Artificial intelligence image feature extraction system and feature identification method thereof | |
CN110619331A (en) | Color distance-based color image field positioning method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180223 |
|
RJ01 | Rejection of invention patent application after publication |